{"id":4083712,"url":"https://alion.io/job/clera-research-engineer-benchmarks-12","title":"Research Engineer, Benchmarks","company":{"id":2706,"name":"Clera","domain":"getclera.com","url":"https://alion.io/company/clera","size_band":"11-50","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":80,"open_postings":40,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":6,"computed_at":"2026-11-12T10:38:37Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"junior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Singapore"],"countries":["SG"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":100000,"max":170000,"currency":"USD","period":"year","gross":null,"usd_annual":170000},"salary_estimate":null,"experience_years_min":2,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Docker","optional":false},{"name":"Linux","optional":false},{"name":"Machine Learning","optional":false},{"name":"Python","optional":false},{"name":"Reinforcement Learning","optional":false}],"status":"live","first_seen_at":"2026-11-11T17:19:40Z","employer_posted_date":"2026-11-11","last_verified_at":"2026-11-12T10:49:39Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"About the Role\nJoin a small, technical AI evaluation team building rigorous benchmarks for frontier AI agents. You will own the design and implementation of domain-specific evaluations that help research teams and customers understand how agents perform on realistic workflows.\nWhat You'll Do\nDesign, implement, and maintain internal benchmarks for evaluating frontier agents on domain-specific tasks.\n\nPartner with subject-matter experts to translate real-world workflows into benchmark tasks and evaluation criteria.\n\nBuild reliable infrastructure to run models and agents against benchmark tasks at scale.\n\nDevelop metrics and analyses to assess benchmark difficulty, reliability, and failure modes.\n\nValidate whether benchmark results align with real-world evaluations and user needs.\n\nWrite clear technical documentation and reports explaining benchmark methods and results.\n\nWhat We're Looking For\nTwo to four years of experience in software engineering, machine learning engineering, or research engineering, including at least two years building AI benchmarks, evaluation infrastructure, or agent environments.\n\nTechnical education or strong fundamentals in a technical field.\n\nProficiency with Python, Docker, and Linux for research or production infrastructure.\n\nHands-on experience designing and operating evaluations or environments for AI agents or large language models.\n\nExperience building reliable model or agent execution infrastructure, developing evaluation metrics or statistical analyses, and validating benchmark performance.\n\nAbility to work with subject-matter experts and understand workflows across technical or business domains.\n\nStrong technical writing, attention to detail, independent problem-solving, and comfort in an early-stage environment.\n\nPublished research or technical writing on AI benchmarks, evaluation methods, or model failure modes is valued. Reinforcement learning pipelines, data generation, and agent evaluation experience are also relevant.\n\nCompensation & Benefits\nBase salary: $100,000 to $170,000 USD annually. Visa sponsorship is available.\nLocation\nOn-site in Singapore, Singapore.","description_format":"text","description_chars":2137,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"Singapore","iso":"SG","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-11-11T18:18:20Z"}],"visa":[{"country":"SG","licensed_sponsor":false,"adverts_offering_sponsorship_24m":6,"sanctioned_now":false,"evidence":"Offered visa sponsorship in 6 of its adverts here in 24 months","filings_12m":null,"filings_prev_12m":null,"green_card_filings_12m":null,"median_offered_wage_usd":null,"route":null,"cap_exempt":false,"checked_at":"2026-11-12T07:36:15+00:00","sources":["Alion: sponsorship offered in the employer's own job adverts (24 months)"],"filings_for_role_12m":0}],"liveness":{"score":38,"band":"fade","label":"Fading","p_open":1,"p_active":0.379,"p_room":1,"age_days":0,"expected_fill_days":6,"reasons":["conf:5","agency","stale_co","velocity","win:early","comp:junior,brand"],"computed_at":"2026-11-12T10:38:37Z"},"pay":{"stated_usd_annual":170000,"is_top_pay":false},"html_url":"https://alion.io/job/clera-research-engineer-benchmarks-12","json_url":"https://alion.io/job/clera-research-engineer-benchmarks-12.json","meta":{"generated_at":"2026-11-12T16:17:26Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":34084,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-13T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":2706},"rest":"https://alion.io/mcp/rest/get_company?id=2706"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fclera-research-engineer-benchmarks-12"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":2,"usd":0.2},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fclera-research-engineer-benchmarks-12"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fclera-research-engineer-benchmarks-12"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/clera-research-engineer-benchmarks-12\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fclera-research-engineer-benchmarks-12"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":4083712}},{"tool":"search_jobs","arguments":{"company":"getclera.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":4083712},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}